© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 26483
    Prev
    Next
    INDEX
    Explanations

    internal dialog or thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /MPL
    -0.09
    ocab
    -0.09
    umlu
    -0.08
    torrent
    -0.08
    _transaksi
    -0.08
     solemn
    -0.08
     ÑĢÑĥкÑĥ
    -0.08
    achuset
    -0.08
    Å¡ÃŃ
    -0.08
    laughter
    -0.08
    POSITIVE LOGITS
     mut
    0.22
     muttered
    0.21
     thought
    0.16
     Ñģебе
    0.16
     thoughts
    0.15
     mum
    0.14
     ÑģобÑĸ
    0.13
     thinking
    0.13
     Thought
    0.12
     Mut
    0.12
    Activations Density 0.074%

    No Known Activations